TensorFlow, PyTorch and Numpy layers for generating Orthogonal Polynomials

Last update: May 25, 2022

Related tags

Deep Learning OrthNet

Overview

OrthNet

TensorFlow, PyTorch and Numpy layers for generating multi-dimensional Orthogonal Polynomials

1. Installation
2. Usage
3. Polynomials
4. Base Class(Poly)

Installation:

the stable version:
pip3 install orthnet
the dev version:

git clone https://github.com/orcuslc/orthnet.git && cd orthnet
python3 setup.py build_ext --inplace && python3 setup.py install

Usage:

with TensorFlow

import tensorflow as tf
import numpy as np
from orthnet import Legendre

x_data = np.random.random((10, 2))
x = tf.placeholder(dtype = tf.float32, shape = [None, 2])
L = Legendre(x, 5)

with tf.Session() as sess:
    print(L.tensor, feed_dict = {x: x_data})

with PyTorch

import torch
import numpy as np
from orthnet import Legendre

x = torch.DoubleTensor(np.random.random((10, 2)))
L = Legendre(x, 5)
print(L.tensor)

with Numpy

import numpy as np
from orthnet import Legendre

x = np.random.random((10, 2))
L = Legendre(x, 5)
print(L.tensor)

Specify Backend

In some scenarios, users can specify the exact backend compatible with the input x. The backends provided are:

An example to specify the backend is as follows.

import numpy as np
from orthnet import Legendre, NumpyBackend

x = np.random.random((10, 2))
L = Legendre(x, 5, backend = NumpyBackend())
print(L.tensor)

Specify tensor product combinations

In some scenarios, users may provide pre-computed tensor product combinations to save computing time. An example of providing combinations is as follows.

import numpy as np
from orthnet import Legendre, enum_dim

dim = 2
degree = 5
x = np.random.random((10, dim))
L = Legendre(x, degree, combinations = enum_dim(degree, dim))
print(L.tensor)

Polynomials:

Class	Polynomial
`orthnet.Legendre(Poly)`	Legendre polynomial
`orthnet.Legendre_Normalized(Poly)`	Normalized Legendre polynomial
`orthnet.Laguerre(Poly)`	Laguerre polynomial
`orthnet.Hermite(Poly)`	Hermite polynomial of the first kind (in probability theory)
`orthnet.Hermite2(Poly)`	Hermite polynomial of the second kind (in physics)
`orthnet.Chebyshev(Poly)`	Chebyshev polynomial of the first kind
`orthnet.Chebyshev2(Poly)`	Chebyshev polynomial of the second kind
`orthnet.Jacobi(Poly, alpha, beta)`	Jacobi polynomial

Base class:

Class Poly(x, degree, combination = None):

Inputs:
- x a tensor
- degree highest degree for target polynomials
- combination optional, tensor product combinations
Attributes:
- Poly.tensor the tensor of function values (with degree from 0 to Poly.degree(included))
- Poly.length the number of function basis (columns) in Poly.tensor
- Poly.index the index of the first combination of each degree in Poly.combinations
- Poly.combinations all combinations of tensor product
- Poly.tensor_of_degree(degree) return all polynomials of given degrees
- Poly.eval(coefficients) return the function values with given coefficients
- Poly.quadrature(function, weight) return Gauss quadrature with given function and weight

Comments

Cuda support

Hi,

First of all thank your for developing this project. Is it possible to create the Jacobi.tensor in the gpu? Currently I am creating the tensor in the cpu and then moving them to gpu, which is time consuming.

Cheers

opened by mariolinovIC 1
Jacobi polynomial incorrect evaluation

Hi, I have noticed than when I evaluate Jacobi polynomial with alpha=1 and beta=1 the results are not ok. Particularly I tried in range (-1,1) and I noticed the problem for n greater than 1 (i.e., 2,3,4). Thank you for your support.

opened by mariolinovIC 0

A repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]

PINTO_model_zoo Please read the contents of the LICENSE file located directly under each folder before using the model. My model conversion scripts ar

2.4k Jan 5, 2023

An Ensemble of CNN (Python 3.5.1 Tensorflow 1.3 numpy 1.13)

0 May 6, 2022

Unofficial PyTorch implementation of Attention Free Transformer (AFT) layers by Apple Inc.

aft-pytorch Unofficial PyTorch implementation of Attention Free Transformer's layers by Zhai, et al. [abs, pdf] from Apple Inc. Installation You can i

184 Dec 12, 2022

A library to inspect itermediate layers of PyTorch models.

A library to inspect itermediate layers of PyTorch models. Why? It's often the case that we want to inspect intermediate layers of a model without mod

380 Dec 28, 2022

a reccurrent neural netowrk that when trained on a peice of text and fed a starting prompt will write its on 250 character text using LSTM layers

RNN-Playwrite a reccurrent neural netowrk that when trained on a peice of text and fed a starting prompt will write its on 250 character text using LS

1 Oct 29, 2021

TensorFlow, PyTorch and Numpy layers for generating Orthogonal Polynomials

Related tags

Overview

OrthNet

Installation:

Usage:

with TensorFlow

with PyTorch

with Numpy

Specify Backend

Specify tensor product combinations

Polynomials:

Base class:

You might also like...

An Ensemble of CNN (Python 3.5.1 Tensorflow 1.3 numpy 1.13)

Unofficial PyTorch implementation of Attention Free Transformer (AFT) layers by Apple Inc.

A library to inspect itermediate layers of PyTorch models.

a reccurrent neural netowrk that when trained on a peice of text and fed a starting prompt will write its on 250 character text using LSTM layers

Meta Language-Specific Layers in Multilingual Language Models

Improving Deep Network Debuggability via Sparse Decision Layers

Spectral Tensor Train Parameterization of Deep Learning Layers

RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition

Comments

Cuda support

Jacobi polynomial incorrect evaluation

Releases(0.4.0)

0.4.0(Apr 19, 2018)

0.3.0(Apr 5, 2018)

0.2.2(Mar 22, 2018)

0.1(Feb 27, 2018)

Owner

Chuan

Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting

Episodic Transformer (E.T.) is a novel attention-based architecture for vision-and-language navigation. E.T. is based on a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions.

[NeurIPS 2021] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining

This repo is customed for VisDrone.

This repo is about implementing different approaches of pose estimation and also is a sub-task of the smart hospital bed project :smile:

Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations

Training neural models with structured signals.

Some pre-commit hooks for OpenMMLab projects

(AAAI 2021) Progressive One-shot Human Parsing

Categorical Depth Distribution Network for Monocular 3D Object Detection

The official code for paper "R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling".

A large dataset of 100k Google Satellite and matching Map images, resembling pix2pix's Google Maps dataset.

GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training @ KDD 2020

HNN: Human (Hollywood) Neural Network

Pytorch for Segmentation

[CoRL 2021] A robotics benchmark for cross-embodiment imitation.

Deep Unsupervised 3D SfM Face Reconstruction Based on Massive Landmark Bundle Adjustment.

Process JSON files for neural recording sessions using Medtronic's BrainSense Percept PC neurostimulator

CAUSE: Causality from AttribUtions on Sequence of Events

From a body shape, infer the anatomic skeleton.